AL amyloidosis presenting with isolated lumbosacral radiculoplexus neuropathy.

A 45-year-old man presented with an isolated sciatic mononeuropathy, which then evolved into a lumbosacral radiculoplexus neuropathy. His initial symptoms included lower limb pain, sensory disturbance and later weakness, without autonomic dysfunction. Neurophysiology suggested a postganglionic neuropathy. MR and ultrasound scans of the thighs showed right sciatic nerve thickening, and CSF analysis showed albuminocytological dissociation. Fluorodeoxyglucose positron emission tomography (FDG PET) was unremarkable. He then developed orthostatic symptoms and urinary disturbance, and was found to have an IgM paraprotein. Fat aspirate, cardiac and whole-body imaging found no amyloid deposition, and genetic testing for transthyretin amyloidosis was negative. A bone marrow biopsy was unremarkable. However, neuropathology review of a proximal, fascicular nerve biopsy identified a lambda chain-restricted plasma cell population with positive Congo red staining, leading to a diagnosis of peripheral nerve restricted amyloid light amyloidosis. We discuss the diagnostic approach to this case from the perspectives of neurology, neurophysiology, radiology and neuropathology.

Ion channels in EEG: isolating channel dysfunction in NMDA receptor antibody encephalitis.

See Roberts and Breakspear (doi:10.1093/brain/awy136) for a scientific commentary on this article.Neurological and psychiatric practice frequently lack diagnostic probes that can assess mechanisms of neuronal communication non-invasively in humans. In N-methyl-d-aspartate (NMDA) receptor antibody encephalitis, functional molecular assays are particularly important given the presence of NMDA antibodies in healthy populations, the multifarious symptomology and the lack of radiological signs. Recent advances in biophysical modelling techniques suggest that inferring cellular-level properties of neural circuits from macroscopic measures of brain activity is possible. Here, we estimated receptor function from EEG in patients with NMDA receptor antibody encephalitis (n = 29) as well as from encephalopathic and neurological patient controls (n = 36). We show that the autoimmune patients exhibit distinct fronto-parietal network changes from which ion channel estimates can be obtained using a microcircuit model. Specifically, a dynamic causal model of EEG data applied to spontaneous brain responses identifies a selective deficit in signalling at NMDA receptors in patients with NMDA receptor antibody encephalitis but not at other ionotropic receptors. Moreover, though these changes are observed across brain regions, these effects predominate at the NMDA receptors of excitatory neurons rather than at inhibitory interneurons. Given that EEG is a ubiquitously available clinical method, our findings suggest a unique re-purposing of EEG data as an assay of brain network dysfunction at the molecular level.

Whole-Brain Neural Dynamics of Probabilistic Reward Prediction.

Predicting future reward is paramount to performing an optimal action. Although a number of brain areas are known to encode such predictions, a detailed account of how the associated representations evolve over time is lacking. Here, we address this question using human magnetoencephalography (MEG) and multivariate analyses of instantaneous activity in reconstructed sources. We overtrained participants on a simple instrumental reward learning task where geometric cues predicted a distribution of possible rewards, from which a sample was revealed 2000 ms later. We show that predicted mean reward (i.e., expected value), and predicted reward variability (i.e., economic risk), are encoded distinctly. Early on, representations of mean reward are seen in parietal and visual areas, and later in frontal regions with orbitofrontal cortex emerging last. Strikingly, an encoding of reward variability emerges simultaneously in parietal/sensory and frontal sources and later than mean reward encoding. An orbitofrontal variability encoding emerged around the same time as that seen for mean reward. Crucially, cross-prediction showed that mean reward and variability representations are distinct and also revealed that instantaneous representations become more stable over time. Across sources, the best fitting metric for variability signals was coefficient of variation (rather than SD or variance), but distinct best metrics were seen for individual brain regions. Our data demonstrate how a dynamic encoding of probabilistic reward prediction unfolds in the brain both in time and space.SIGNIFICANCE STATEMENT Predicting future reward is paramount to optimal behavior. To gain insight into the underlying neural computations, we investigate how reward representations in the brain arise over time. Using magnetoencephalography, we show that a representation of predicted mean reward emerges early in parietal/sensory regions and later in frontal cortex. In contrast, predicted reward variability representations appear in most regions at the same time, and slightly later than for mean reward. For both features, representations dynamically change >1000 ms before stabilizing. The best metric for encoding variability is coefficient of variation, with heterogeneity in this encoding seen between brain areas. The results provide novel insights into the emergence of predictive reward representations.

Chronic non-freezing cold injury results in neuropathic pain due to a sensory neuropathy.

Non-freezing cold injury develops after sustained exposure to cold temperatures, resulting in tissue cooling but not freezing. This can result in persistent sensory disturbance of the hands and feet including numbness, paraesthesia and chronic pain. Both vascular and neurological aetiologies of this pain have been suggested but remain unproven. We prospectively approached patients referred for clinical assessment of chronic pain following non-freezing cold injury between 12 February 2014 and 30 November 2016. Of 47 patients approached, 42 consented to undergo detailed neurological evaluations including: questionnaires to detail pain location and characteristics, structured neurological examination, quantitative sensory testing, nerve conduction studies and skin biopsy for intraepidermal nerve fibre assessment. Of the 42 study participants, all had experienced non-freezing cold injury while serving in the UK armed services and the majority were of African descent (76.2%) and male (95.2%). Many participants reported multiple exposures to cold. The median time between initial injury and referral was 3.72 years. Pain was principally localized to the hands and the feet, neuropathic in nature and in all study participants associated with cold hypersensitivity. Clinical examination and quantitative sensory testing were consistent with a sensory neuropathy. In all cases, large fibre nerve conduction studies were normal. The intraepidermal nerve fibre density was markedly reduced with 90.5% of participants having a count at or below the 0.05 centile of published normative controls. Using the Neuropathic Pain Special Interest Group of the International Association for the Study of Pain grading for neuropathic pain, 100% had probable and 95.2% definite neuropathic pain. Chronic non-freezing cold injury is a disabling neuropathic pain disorder due to a sensory neuropathy. Why some individuals develop an acute painful sensory neuropathy on sustained cold exposure is not yet known, but individuals of African descent appear vulnerable. Screening tools, such as the DN4 questionnaire, and treatment algorithms for neuropathic pain should now be used in the management of these patients.

A mathematical model of cellular swelling in Neuromyelitis optica.

Neuromyelitis Optica (NMO) is a severe neuro-inflammatory disease of the central nervous system characterized by predominant damage to the optic nerve and of the spinal cord. The pathogenic antibody found in the majority of patients targets the AQP4 channels on astrocytic endfeet and causes the cells to swell. Although, the pathophysiology of the disease is broadly known, there are no specific targeted treatments for this process clinically available nor accurate prognostic markers both during attacks and for predicting long term neuronal damage. This lack is, in part, due to the rarity of the disease and its relatively recent pathogenic clarity. Hence, the ability to mathematically model the progress of the condition to test prospective therapies in silico would be a step forward. This paper combines state of the art models of cellular metabolism and cytotoxic oedema in neurons and astrocytes and augments it with a detailed characterization of water transport across the cellular membrane. In particular, we capture the process of perforation of the cell through the human complement cascade and resulting water and ionic fluxes. Simulating NMO by injecting its antibody and human complement into the extracellular space showed a 25% increase of the astrocytic volume after 12 h from onset. Most of the volume change occurred during the first 30 min of simulation with a peak volume change of 38%. The model was further adapted to simulate the therapeutic potential of CD59. It was found that there is a threshold of CD59 concentration that can prevent the swelling of astrocytes. Since the astrocyte volume changes mostly during the first hour, further experimental work should focus on this time scale to provide data for further model refinement and validation.

Profiling neuronal ion channelopathies with non-invasive brain imaging and dynamic causal models: Case studies of single gene mutations.

Clinical assessments of brain function rely upon visual inspection of electroencephalographic waveform abnormalities in tandem with functional magnetic resonance imaging. However, no current technology proffers in vivo assessments of activity at synapses, receptors and ion-channels, the basis of neuronal communication. Using dynamic causal modeling we compared electrophysiological responses from two patients with distinct monogenic ion channelopathies and a large cohort of healthy controls to demonstrate the feasibility of assaying synaptic-level channel communication non-invasively. Synaptic channel abnormality was identified in both patients (100% sensitivity) with assay specificity above 89%, furnishing estimates of neurotransmitter and voltage-gated ion throughput of sodium, calcium, chloride and potassium. This performance indicates a potential novel application as an adjunct for clinical assessments in neurological and psychiatric settings. More broadly, these findings indicate that biophysical models of synaptic channels can be estimated non-invasively, having important implications for advancing human neuroimaging to the level of non-invasive ion channel assays.

The brain ages optimally to model its environment: evidence from sensory learning over the adult lifespan.

The aging brain shows a progressive loss of neuropil, which is accompanied by subtle changes in neuronal plasticity, sensory learning and memory. Neurophysiologically, aging attenuates evoked responses--including the mismatch negativity (MMN). This is accompanied by a shift in cortical responsivity from sensory (posterior) regions to executive (anterior) regions, which has been interpreted as a compensatory response for cognitive decline. Theoretical neurobiology offers a simpler explanation for all of these effects--from a Bayesian perspective, as the brain is progressively optimized to model its world, its complexity will decrease. A corollary of this complexity reduction is an attenuation of Bayesian updating or sensory learning. Here we confirmed this hypothesis using magnetoencephalographic recordings of the mismatch negativity elicited in a large cohort of human subjects, in their third to ninth decade. Employing dynamic causal modeling to assay the synaptic mechanisms underlying these non-invasive recordings, we found a selective age-related attenuation of synaptic connectivity changes that underpin rapid sensory learning. In contrast, baseline synaptic connectivity strengths were consistently strong over the decades. Our findings suggest that the lifetime accrual of sensory experience optimizes functional brain architectures to enable efficient and generalizable predictions of the world.

Free energy, precision and learning: the role of cholinergic neuromodulation.

Acetylcholine (ACh) is a neuromodulatory transmitter implicated in perception and learning under uncertainty. This study combined computational simulations and pharmaco-electroencephalography in humans, to test a formulation of perceptual inference based upon the free energy principle. This formulation suggests that ACh enhances the precision of bottom-up synaptic transmission in cortical hierarchies by optimizing the gain of supragranular pyramidal cells. Simulations of a mismatch negativity paradigm predicted a rapid trial-by-trial suppression of evoked sensory prediction error (PE) responses that is attenuated by cholinergic neuromodulation. We confirmed this prediction empirically with a placebo-controlled study of cholinesterase inhibition. Furthermore, using dynamic causal modeling, we found that drug-induced differences in PE responses could be explained by gain modulation in supragranular pyramidal cells in primary sensory cortex. This suggests that ACh adaptively enhances sensory precision by boosting bottom-up signaling when stimuli are predictable, enabling the brain to respond optimally under different levels of environmental uncertainty.

Multimodal wearable EEG, EMG and accelerometry measurements improve the accuracy of tonic-clonic seizure detection.

Objective. This paper aims to investigate the possibility of detecting tonic-clonic seizures (TCSs) with behind-the-ear, two-channel wearable electroencephalography (EEG), and to evaluate its added value to non-EEG modalities in TCS detection.Methods. We included 27 participants with a total of 44 TCSs from the European multicenter study SeizeIT2. The wearable Sensor Dot (Byteflies) was used to measure behind-the-ear EEG, electromyography (EMG), electrocardiography, accelerometry (ACC) and gyroscope. We evaluated automatic unimodal detection of TCSs, using sensitivity, precision, false positive rate (FPR) and F1-score. Subsequently, we fused the different modalities and again assessed performance. Algorithm-labeled segments were then provided to two experts, who annotated true positive TCSs, and discarded false positives.Results. Wearable EEG outperformed the other single modalities with a sensitivity of 100% and a FPR of 10.3/24 h. The combination of wearable EEG and EMG proved most clinically useful, delivering a sensitivity of 97.7%, an FPR of 0.4/24 h, a precision of 43%, and an F1-score of 59.7%. The highest overall performance was achieved through the fusion of wearable EEG, EMG, and ACC, yielding a sensitivity of 90.9%, an FPR of 0.1/24 h, a precision of 75.5%, and an F1-score of 82.5%.Conclusions. In TCS detection with a wearable device, combining EEG with EMG, ACC or both resulted in a remarkable reduction of FPR, while retaining a high sensitivity.Significance. Adding wearable EEG could further improve TCS detection, relative to extracerebral-based systems.

Approach-avoidance processes contribute to dissociable impacts of risk and loss on choice.

Value-based choices are influenced both by risk in potential outcomes and by whether outcomes reflect potential gains or losses. These variables are held to be related in a specific fashion, manifest in risk aversion for gains and risk seeking for losses. Instead, we hypothesized that there are independent impacts of risk and loss on choice such that, depending on context, subjects can show either risk aversion for gains and risk seeking for losses or the exact opposite. We demonstrate this independence in a gambling task, by selectively reversing a loss-induced effect (causing more gambling for gains than losses and the reverse) while leaving risk aversion unaffected. Consistent with these dissociable behavioral impacts of risk and loss, fMRI data revealed dissociable neural correlates of these variables, with parietal cortex tracking risk and orbitofrontal cortex and striatum tracking loss. Based on our neural data, we hypothesized that risk and loss influence action selection through approach-avoidance mechanisms, a hypothesis supported in an experiment in which we show valence and risk-dependent reaction time effects in line with this putative mechanism. We suggest that in the choice process risk and loss can independently engage approach-avoidance mechanisms. This can provide a novel explanation for how risk influences action selection and explains both classically described choice behavior as well as behavioral patterns not predicted by existing theory.

Distinct encoding of risk and value in economic choice between multiple risky options.

Neural encoding of value-based stimuli is suggested to involve representations of summary statistics, including risk and expected value (EV). A more complex, but ecologically more common, context is when multiple risky options are evaluated together. However, it is unknown whether encoding related to option evaluation in these situations involves similar principles. Here we employed fMRI during a task that parametrically manipulated EV and risk in two simultaneously presented lotteries, both of which contained either gains or losses. We found representations of EV in medial prefrontal cortex and anterior insula, an encoding that was dependent on which option was chosen (i.e. chosen and unchosen EV) and whether the choice was over gains or losses. Parietal activity reflected whether the riskier or surer option was selected, whilst activity in a network of regions that also included parietal cortex reflected both combined risk and difference in risk for the two options. Our findings provide support for the idea that summary statistics underpin a representation of value-based stimuli, and further that these summary statistics undergo distinct forms of encoding.

Neural segregation of objective and contextual aspects of fairness.

Perception of fairness can influence outcomes in human exchange. However, an inherent subjectivity in attribution renders it difficult to manipulate fairness experimentally. Here using a modified ultimatum game, within a varying social context, we induced a bias in human subjects' acceptance of objectively identical offers. To explain this fairness-related behavior, we use a computational model to specify metrics for the objective and contextual aspects of fairness, testing for correlations between these model parameters and brain activity determined using functional magnetic resonance imaging. We show that objective social inequality, as defined by our model, is tracked in posterior insula cortex. Crucially, this inequality is integrated with social context in posterior and mid-insula, consistent with construction of a fairness motivation that flexibly adapted to the social environment. We suggest that the dual importance of objective and contextual aspects to fairness we highlight might explain seemingly inconsistent societal phenomena, including public attitudes to income disparities.

Dopamine agonists and risk: impulse control disorders in Parkinson's disease.

Impulse control disorders are common in Parkinson's disease, occurring in 13.6% of patients. Using a pharmacological manipulation and a novel risk taking task while performing functional magnetic resonance imaging, we investigated the relationship between dopamine agonists and risk taking in patients with Parkinson's disease with and without impulse control disorders. During functional magnetic resonance imaging, subjects chose between two choices of equal expected value: a 'Sure' choice and a 'Gamble' choice of moderate risk. To commence each trial, in the 'Gain' condition, individuals started at $0 and in the 'Loss' condition individuals started at -$50 below the 'Sure' amount. The difference between the maximum and minimum outcomes from each gamble (i.e. range) was used as an index of risk ('Gamble Risk'). Sixteen healthy volunteers were behaviourally tested. Fourteen impulse control disorder (problem gambling or compulsive shopping) and 14 matched Parkinson's disease controls were tested ON and OFF dopamine agonists. Patients with impulse control disorder made more risky choices in the 'Gain' relative to the 'Loss' condition along with decreased orbitofrontal cortex and anterior cingulate activity, with the opposite observed in Parkinson's disease controls. In patients with impulse control disorder, dopamine agonists were associated with enhanced sensitivity to risk along with decreased ventral striatal activity again with the opposite in Parkinson's disease controls. Patients with impulse control disorder appear to have a bias towards risky choices independent of the effect of loss aversion. Dopamine agonists enhance sensitivity to risk in patients with impulse control disorder possibly by impairing risk evaluation in the striatum. Our results provide a potential explanation of why dopamine agonists may lead to an unconscious bias towards risk in susceptible individuals.

The clinical relevance of serum versus CSF NMDAR autoantibodies associated exclusively with psychiatric features: a systematic review and meta-analysis of individual patient data.

BACKGROUND: A variety of psychiatric syndromes are associated with NMDAR autoantibodies; however, their clinical relevance when only present in the serum is unclear. We explored whether patients with CSF NMDAR autoantibodies could be distinguished from patients with serum-only NMDAR autoantibodies. METHODS: The electronic databases MEDLINE, EMBASE, PubMed, and PsycINFO were searched. Articles reporting adult patients with isolated psychiatric features and positive for NMDAR autoantibodies with relevant investigations were included. Patient level meta-analysis compared patients positive for CSF NMDAR autoantibodies with patients positive for serum NMDAR autoantibodies, but negative for CSF NMDAR autoantibodies. Dichotomous data were analysed using crude odds ratios (OR), whilst continuous data were analysed using Mann-Whitney Test (U). The protocol was prospectively registered (CRD42018082210). RESULTS: Of 4413 publications, 42 were included, reporting 79 patients. Median age was 34 years (IQR 19 years); 56% (45/79) were female and 24% (16/68) had a tumour. In total, 41 patients were positive for CSF autoantibodies and 20 were positive for serum-only autoantibodies. Patients with CSF autoantibodies were significantly more likely to be female (p < 0.001) and have a rapid (< 3 month) onset of symptoms (p = 0.02) than patients with serum-only autoantibodies. They were also more likely to present with psychosis (p < 0.001), exhibit EEG (p = 0.006), MRI (p = 0.002), and CSF (p = 0.001) abnormalities, but less likely to present with insomnia (p = 0.04). CONCLUSIONS: Patients with an isolated psychiatric syndrome with CSF NMDAR autoantibodies can potentially be distinguished from those with serum-only NMDAR autoantibodies based on clinicodemographic and investigation findings.

A behavioral and neural evaluation of prospective decision-making under risk.

Making the best choice when faced with a chain of decisions requires a person to judge both anticipated outcomes and future actions. Although economic decision-making models account for both risk and reward in single-choice contexts, there is a dearth of similar knowledge about sequential choice. Classical utility-based models assume that decision-makers select and follow an optimal predetermined strategy, regardless of the particular order in which options are presented. An alternative model involves continuously reevaluating decision utilities, without prescribing a specific future set of choices. Here, using behavioral and functional magnetic resonance imaging (fMRI) data, we studied human subjects in a sequential choice task and use these data to compare alternative decision models of valuation and strategy selection. We provide evidence that subjects adopt a model of reevaluating decision utilities, in which available strategies are continuously updated and combined in assessing action values. We validate this model by using simultaneously acquired fMRI data to show that sequential choice evokes a pattern of neural response consistent with a tracking of anticipated distribution of future reward, as expected in such a model. Thus, brain activity evoked at each decision point reflects the expected mean, variance, and skewness of possible payoffs, consistent with the idea that sequential choice evokes a prospective evaluation of both available strategies and possible outcomes.

Deconstructing risk: separable encoding of variance and skewness in the brain.

Risky choice entails a need to appraise all possible outcomes and integrate this information with individual risk preference. Risk is frequently quantified solely by statistical variance of outcomes, but here we provide evidence that individuals' choice behaviour is sensitive to both dispersion (variance) and asymmetry (skewness) of outcomes. Using a novel behavioural paradigm in humans, we independently manipulated these 'summary statistics' while scanning subjects with fMRI. We show that a behavioural sensitivity to variance and skewness is mirrored in neuroanatomically dissociable representations of these quantities, with parietal cortex showing sensitivity to the former and prefrontal cortex and ventral striatum to the latter. Furthermore, integration of these objective risk metrics with subjective risk preference is expressed in a subject-specific coupling between neural activity and choice behaviour in anterior insula. Our findings show that risk is neither monolithic from a behavioural nor neural perspective and its decomposition is evident both in distinct behavioural preferences and in segregated underlying brain representations.

Proof of concept: Screening for REM sleep behaviour disorder with a minimal set of sensors.

OBJECTIVE: Rapid-Eye-Movement (REM) sleep behaviour disorder (RBD) is an early predictor of Parkinson's disease, dementia with Lewy bodies, and multiple system atrophy. This study investigated the use of a minimal set of sensors to achieve effective screening for RBD in the population, integrating automated sleep staging (three state) followed by RBD detection without the need for cumbersome electroencephalogram (EEG) sensors. METHODS: Polysomnography signals from 50 participants with RBD and 50 age-matched healthy controls were used to evaluate this study. Three stage sleep classification was achieved using a random forest classifier and features derived from a combination of cost-effective and easy to use sensors, namely electrocardiogram (ECG), electrooculogram (EOG), and electromyogram (EMG) channels. Subsequently, RBD detection was achieved using established and new metrics derived from ECG and EMG channels. RESULTS: The EOG and EMG combination provided the optimal minimalist fully-automated performance, achieving 0.57 ± 0.19 kappa (3 stage) for sleep staging and an RBD detection accuracy of 0.90 ± 0.11, (sensitivity and specificity of 0.88 ± 0.13 and 0.92 ± 0.098, respectively). A single ECG sensor achieved three state sleep staging with 0.28 ± 0.06 kappa and RBD detection accuracy of 0.62 ± 0.10. CONCLUSIONS: This study demonstrates the feasibility of using signals from a single EOG and EMG sensor to detect RBD using fully-automated techniques. SIGNIFICANCE: This study proposes a cost-effective, practical, and simple RBD identification support tool using only two sensors (EMG and EOG); ideal for screening purposes.

An Investigation of Levetiracetam in Alzheimer's Disease (ILiAD): a double-blind, placebo-controlled, randomised crossover proof of concept study.

BACKGROUND: Although Alzheimer's disease affects around 800,000 people in the UK and costs almost £23 billion per year, currently licenced treatments only offer modest benefit at best. Seizures, which are more common in patients with Alzheimer's disease than age matched controls, may contribute to the loss of nerve cells and abnormal brain discharges can disrupt cognition. This aberrant electrical activity may therefore present potentially important drug targets. The anti-seizure medication levetiracetam can reduce abnormal cortical discharges and reverse memory deficits in a mouse model of Alzheimer's disease. Levetiracetam has also been shown to improve memory difficulties in patients with mild cognitive impairment, a precursor to Alzheimer's disease. Clinical use of levetiracetam is well-established in treatment of epilepsy and extensive safety data are available. Levetiracetam thus has the potential to provide safe and efficacious treatment to help with memory difficulties in Alzheimer's disease. METHODS: The proposed project is a proof of concept study to test whether levetiracetam can help cognitive function in people with dementia. We plan to recruit thirty patients with mild to moderate Alzheimer's disease with no history of previous seizures or other significant co-morbidity. Participants will be allocated to a double-blind placebo-controlled crossover trial that tests levetiracetam against placebo. Standardised scales to assess cognition and a computer-based touchscreen test that we have developed to better detect subtle improvements in hippocampal function will be used to measure changes in memory. All participants will have an electroencephalogram (EEG) at baseline. The primary outcome measure is a change in the computer-based touchscreen cognitive task while secondary outcomes include the effect of levetiracetam on mood, quality of life and modelling of the EEG, including time series measures and feature-based analysis to see whether the effect of levetiracetam can be predicted. The effect of levetiracetam and placebo will be compared within a given patient using the paired t-test and the analysis of covariance adjusting for baseline values. DISCUSSION: This is the first study to evaluate if an anti-seizure medication can offer meaningful benefit to patients with Alzheimer's disease. If this study demonstrates at least stabilisation of memory function and/or good tolerability, the next step will be to rapidly progress to a larger study to establish whether levetiracetam may be a useful and cost-effective treatment for patients with Alzheimer's disease. TRIAL REGISTRATION: ClinicalTrials.gov NCT03489044 . Registered on April 5, 2018.

Detection of REM sleep behaviour disorder by automated polysomnography analysis.

OBJECTIVE: Evidence suggests Rapid-Eye-Movement (REM) Sleep Behaviour Disorder (RBD) is an early predictor of Parkinson's disease. This study proposes a fully-automated framework for RBD detection consisting of automated sleep staging followed by RBD identification. METHODS: Analysis was assessed using a limited polysomnography montage from 53 participants with RBD and 53 age-matched healthy controls. Sleep stage classification was achieved using a Random Forest (RF) classifier and 156 features extracted from electroencephalogram (EEG), electrooculogram (EOG) and electromyogram (EMG) channels. For RBD detection, a RF classifier was trained combining established techniques to quantify muscle atonia with additional features that incorporate sleep architecture and the EMG fractal exponent. RESULTS: Automated multi-state sleep staging achieved a 0.62 Cohen's Kappa score. RBD detection accuracy improved from 86% to 96% (compared to individual established metrics) when using manually annotated sleep staging. Accuracy remained high (92%) when using automated sleep staging. CONCLUSIONS: This study outperforms established metrics and demonstrates that incorporating sleep architecture and sleep stage transitions can benefit RBD detection. This study also achieved automated sleep staging with a level of accuracy comparable to manual annotation. SIGNIFICANCE: This study validates a tractable, fully-automated, and sensitive pipeline for RBD identification that could be translated to wearable take-home technology.